What is MCP in AI?

Anthropic introduced it in late 2024, and today many apps and models support it. The idea is a bit like a USB port: instead of building a different integration for every assistant, you build an MCP server once and any compatible client can use it.

An MCP server offers tools (actions, like creating a ticket), resources (data, like files or records) and prompts. The assistant sees what is available and decides when to use it.

Because it gives the model access to real systems, it is wise to install servers only from trusted sources and to check what permissions they ask for.

Related terms

• AI agent: An AI agent is a system where a model does more than answer: it decides on steps, uses tools and acts in a loop until it reaches a goal.
• LLM (large language model): An LLM (large language model) is an AI model trained on huge amounts of text to predict the next token. It is the engine behind ChatGPT, Claude and Gemini.
• Prompt: A prompt is the instruction or text you give an AI model so it responds. The clearer the context and the goal, the better the answer tends to be.